Part 1: PCA with penguins

penguin_pca <- penguins %>% 
  select(body_mass_g, ends_with("_mm")) %>% 
  drop_na() %>% 
  scale() %>% 
  prcomp()


penguin_complete <- penguins %>% 
  drop_na(body_mass_g, ends_with("_mm"))

autoplot(penguin_pca,
         data = penguin_complete,
         colour = 'species',
         loadings = TRUE,
         loadings.label = TRUE) +
  theme_minimal()
## Warning: `select_()` is deprecated as of dplyr 0.7.0.
## Please use `select()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.

Part 2: GGplot customization and reading in different file types

Read in a .xlsx file and do some wrangling
fish_noaa <- read_excel(here("data", "foss_landings.xlsx")) %>% 
  clean_names() %>% 
  mutate(across(where(is.character), tolower)) %>%
  mutate(nmfs_name = str_sub(nmfs_name, end = -4)) %>% 
  filter(confidentiality == "public")

Make a customized graph:

fish_plot <- ggplot(data = fish_noaa, aes(x = year, y = pounds)) +
  geom_line(aes(color = nmfs_name), show.legend = FALSE) +
  theme_minimal()

fish_plot
## Warning: Removed 6 rows containing missing values (geom_path).

ggplotly(fish_plot)
### Use gghighlight to highlight certain series
ggplot(data = fish_noaa, aes(x = year, y = pounds, group = nmfs_name)) +
  geom_line() +
  theme_minimal() +
  gghighlight(max(pounds) > 1e8)
## label_key: nmfs_name
## Warning: Removed 6 rows containing missing values (geom_path).

Read in data from a url, lubridate(), mutate(), make a graph with months in logical order
monroe_wt <- read_csv("https://data.bloomington.in.gov/dataset/2c81cfe3-62c2-46ed-8fcf-83c1880301d1/resource/13c8f7aa-af51-4008-80a9-56415c7c931e/download/mwtpdailyelectricitybclear.csv") %>% 
  clean_names()
## Parsed with column specification:
## cols(
##   date = col_character(),
##   kWh1 = col_double(),
##   kW1 = col_double(),
##   kWh2 = col_double(),
##   kW2 = col_double(),
##   solar_kWh = col_double(),
##   total_kWh = col_double(),
##   MG = col_double()
## )
monroe_ts <- monroe_wt %>% 
  mutate(date = mdy(date)) %>% 
  mutate(record_month = month(date)) %>% 
  mutate(month_name = month.abb[record_month]) %>% 
  mutate(month_name = fct_reorder(month_name, record_month))

ggplot(data = monroe_ts, aes(month_name, y = total_k_wh)) +
  geom_jitter() +
  theme_minimal()

Part 3: Compound figures with patchwork

Patchwork is very cool, there’s all kinds of customizing stuff you can do.

graph_a <- ggplot(data = penguins, aes(x = body_mass_g, y = flipper_length_mm)) +
  geom_point()

graph_b <- ggplot(data = penguins, aes(x = species, y = flipper_length_mm)) +
  geom_jitter(aes(color = species), show.legend = FALSE)

# Use | to put graphs side by side
# Use / to put graphs one over the other

graph_c <- (graph_a | graph_b)/fish_plot & theme_dark()

graph_c
## Warning: Removed 2 rows containing missing values (geom_point).

## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 6 rows containing missing values (geom_path).

ggsave(here("fig", "graph_c_az.png"), width = 5, height = 6)
## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 2 rows containing missing values (geom_point).
## Warning: Removed 6 rows containing missing values (geom_path).